developer_uid: rirv938
submission_id: chaiml-mistral-24b-2048_87004_v2
model_name: chaiml-mistral-24b-2048_87004_v2
model_group: ChaiML/mistral_24b_2048_
status: inactive
timestamp: 2026-01-08T05:17:21+00:00
num_battles: 13382
num_wins: 6598
celo_rating: 1290.59
family_friendly_score: 0.5278
family_friendly_standard_error: 0.007060129743850322
submission_type: basic
model_repo: ChaiML/mistral_24b_2048_old_dataset_v1_172_merged
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 96
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3531829477402975, 'latency_mean': 2.831316125392914, 'latency_p50': 2.839431405067444, 'latency_p90': 3.0354023456573485}, {'batch_size': 2, 'throughput': 0.5561290384488042, 'latency_mean': 3.593384865522385, 'latency_p50': 3.5832324028015137, 'latency_p90': 3.8929382085800173}, {'batch_size': 3, 'throughput': 0.6950140545757878, 'latency_mean': 4.310213412046433, 'latency_p50': 4.285839676856995, 'latency_p90': 4.589328169822693}, {'batch_size': 4, 'throughput': 0.7844910874136349, 'latency_mean': 5.079672967195511, 'latency_p50': 5.049297213554382, 'latency_p90': 5.574640107154846}, {'batch_size': 5, 'throughput': 0.8530094311508873, 'latency_mean': 5.817106541395187, 'latency_p50': 5.831947326660156, 'latency_p90': 6.21929349899292}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-mistral-24b-2048_87004_v2
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/mistral_24b_2048_old_dataset_v1_172_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 0.58
us_pacific_date: 2026-01-07
win_ratio: 0.49305036616350323
generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 60, 'presence_penalty': 0.1, 'frequency_penalty': 0.0, 'stopping_words': ['<|im_end|>', '<|im_start|>', 'You:', '###', '</s>', '\n'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 96}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-mistral-24b-2048-87004-v2-mkmlizer
Waiting for job on chaiml-mistral-24b-2048-87004-v2-mkmlizer to finish
chaiml-mistral-24b-2048-87004-v2-mkmlizer: bash: cannot set terminal process group (-1): Inappropriate ioctl for device
chaiml-mistral-24b-2048-87004-v2-mkmlizer: bash: no job control in this shell
chaiml-mistral-24b-2048-87004-v2-mkmlizer: /root/miniconda3/envs/nvidia/lib/python3.11/site-packages/mk1/__init__.py:1: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
chaiml-mistral-24b-2048-87004-v2-mkmlizer:   __import__('pkg_resources').declare_namespace(__name__)
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║  Version: 0.30.6+torch280                                           ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ║                                                                     ║
chaiml-mistral-24b-2048-87004-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral-24b-2048-87004-v2-mkmlizer: Downloaded to shared memory in 89.776s
chaiml-mistral-24b-2048-87004-v2-mkmlizer: Checking if ChaiML/mistral_24b_2048_old_dataset_v1_172_merged already exists in ChaiML
chaiml-mistral-24b-2048-87004-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp0im2z56m, device:0
chaiml-mistral-24b-2048-87004-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral-24b-2048-87004-v2-mkmlizer: The tokenizer you are loading from '/tmp/tmp0im2z56m' with an incorrect regex pattern: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/discussions/84#69121093e8b480e709447d5e. This will lead to incorrect tokenization. You should set the `fix_mistral_regex=True` flag when loading this tokenizer to fix this issue.
chaiml-mistral-24b-2048-87004-v2-mkmlizer: quantized model in 287.602s
chaiml-mistral-24b-2048-87004-v2-mkmlizer: Processed model ChaiML/mistral_24b_2048_old_dataset_v1_172_merged in 377.379s
chaiml-mistral-24b-2048-87004-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral-24b-2048-87004-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral-24b-2048-87004-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral-24b-2048-87004-v2/nvidia
chaiml-mistral-24b-2048-87004-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-87004-v2/nvidia/config.json
chaiml-mistral-24b-2048-87004-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-87004-v2/nvidia/tokenizer_config.json
chaiml-mistral-24b-2048-87004-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral-24b-2048-87004-v2/nvidia/special_tokens_map.json
chaiml-mistral-24b-2048-87004-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-2048-87004-v2/nvidia/flywheel_model.1.safetensors
chaiml-mistral-24b-2048-87004-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral-24b-2048-87004-v2/nvidia/flywheel_model.0.safetensors
Job chaiml-mistral-24b-2048-87004-v2-mkmlizer completed after 510.08s with status: succeeded
Stopping job with name chaiml-mistral-24b-2048-87004-v2-mkmlizer
Pipeline stage MKMLizer completed in 510.53s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral-24b-2048-87004-v2
Waiting for inference service chaiml-mistral-24b-2048-87004-v2 to be ready
Inference service chaiml-mistral-24b-2048-87004-v2 ready after 160.93299007415771s
Pipeline stage MKMLDeployer completed in 161.44s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.751537322998047s
Received healthy response to inference request in 2.824828863143921s
Received healthy response to inference request in 2.5284500122070312s
Received healthy response to inference request in 2.2543976306915283s
Received healthy response to inference request in 2.7687933444976807s
5 requests
0 failed requests
5th percentile: 2.309208106994629
10th percentile: 2.3640185832977294
20th percentile: 2.4736395359039305
30th percentile: 2.573067474365234
40th percentile: 2.6623023986816405
50th percentile: 2.751537322998047
60th percentile: 2.7584397315979006
70th percentile: 2.765342140197754
80th percentile: 2.7800004482269287
90th percentile: 2.802414655685425
95th percentile: 2.813621759414673
99th percentile: 2.8225874423980715
mean time: 2.6256014347076415
Pipeline stage StressChecker completed in 14.26s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.63s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.56s
Shutdown handler de-registered
chaiml-mistral-24b-2048_87004_v2 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Generating Leaderboard row for %s
Generated Leaderboard row for %s
Pipeline stage OfflineFamilyFriendlyScorer completed in 2558.19s
Shutdown handler de-registered
chaiml-mistral-24b-2048_87004_v2 status is now inactive due to auto deactivation removed underperforming models